cs.AI（2025-02-20）

📊 共 20 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysis FetalCLIP：用于胎儿超声图像分析的视觉-语言基础模型 foundation model multimodal
2 Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework 提出CHARGE框架与Chart-MRAG Bench，用于评估图表场景下的多模态RAG multimodal ✅
3 EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration EAGER-LLM：通过外生行为-语义集成增强LLM作为推荐器的能力 large language model
4 Multimodal Quantitative Language for Generative Recommendation 提出MQL4GRec，通过多模态量化语言实现生成式推荐的知识迁移。 multimodal
5 WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models WavRAG：面向语音对话模型的音频集成检索增强生成框架 large language model chain-of-thought
6 EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations EquivaMap：利用LLM自动进行优化公式的等价性检查 large language model
7 An LLM-Based Approach for Insight Generation in Data Analysis 提出基于LLM的洞察生成方法，用于从多表数据库中自动提取文本洞察 large language model
8 Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents Vending-Bench：用于评估自主Agent长期连贯性的自动售货机基准测试 large language model
9 Plan-over-Graph: Towards Parallelable LLM Agent Schedule 提出Plan-over-Graph方法，实现LLM Agent任务规划的并行化调度 large language model ✅
10 Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning 提出RetrievalPRM，解决数学推理中过程奖励模型泛化性不足问题 large language model
11 FlowAgent: Achieving Compliance and Flexibility for Workflow Agents FlowAgent：兼顾工作流代理的合规性与灵活性 large language model ✅
12 Investigating the Impact of LLM Personality on Cognitive Bias Manifestation in Automated Decision-Making Tasks 研究LLM人格特质对自动化决策中认知偏差的影响，并探索缓解策略。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
13 External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation 提出ExFM框架，高效服务在线广告推荐中参数规模达万亿级别的外部大型基础模型。 distillation foundation model
14 SPRIG: Stackelberg Perception-Reinforcement Learning with Internal Game Dynamics SPRIG：基于内部博弈动态的Stackelberg感知-强化学习框架 reinforcement learning deep reinforcement learning PPO
15 Making Universal Policies Universal 提出跨智能体通用策略学习方法，解决异构动作空间下的通用决策问题 policy learning imitation learning generalist agent
16 Discovering highly efficient low-weight quantum error-correcting codes with reinforcement learning 提出基于强化学习的量子纠错码优化方法，显著降低物理量子比特开销。 reinforcement learning
17 HPS: Hard Preference Sampling for Human Preference Alignment 提出Hard Preference Sampling (HPS)框架，用于提升LLM人类偏好对齐的鲁棒性和效率。 RLHF large language model
18 Causal Mean Field Multi-Agent Reinforcement Learning 提出因果平均场Q学习（CMFQ）算法，提升多智能体强化学习在非平稳环境下的可扩展性。 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
19 Multi-Agent Coordination across Diverse Applications: A Survey 多智能体协同综述：跨领域应用中的协同机制与未来方向 humanoid large language model
20 Towards Secure Program Partitioning for Smart Contracts with LLM's In-Context Learning PartitionGPT：利用LLM上下文学习实现智能合约安全程序划分 manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页